writing-plans

Break design into 2-5 minute tasks with verification steps.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "writing-plans" with this command: npx skills add nefas11/writing-plans-2

Writing Plans Skill

When to Use

After design approval (brainstorming complete).

Task Structure

Each task must have:

  1. Goal (1 sentence)
  2. Files (exact paths)
  3. Implementation (code snippet or pseudo-code)
  4. Verification (command to run + expected output)
  5. Estimated Time (2-5 min ideal)

Plan Template

# Implementation Plan: [Feature Name]

## Tasks

### Task 1: [Goal]
**Files:** `src/file.js`
**Implementation:**
```javascript
// Add function here
function cacheFetch(key) {
  // ...
}

Verification:

npm test -- cache.test.js
# Expected: 1 passing

Estimated Time: 3 min

Task 2: [Goal]

[... repeat]


Save to: `docs/plans/YYYY-MM-DD-feature-name.md`

## Quality Checklist

Before finalizing plan:
- [ ] Every task has exact file paths
- [ ] Every task has verification command
- [ ] No task >5 min (if yes, split)
- [ ] Tasks are ordered (dependencies first)
- [ ] Plan is reviewable (concrete, not vague)

## Anti-Patterns

❌ Vague tasks ("Improve caching")
❌ No verification steps
❌ Tasks without file paths
❌ Monster tasks (>10 min)

## Example

Bad Task:

Task 1: Add caching

  • Implement cache layer

Good Task:

Task 1: Add in-memory cache for API responses Files: src/cache.js (new), src/api.js (modify) Implementation:

// cache.js
const cache = new Map();
export function get(key) { return cache.get(key); }
export function set(key, val, ttl) { 
  cache.set(key, val);
  setTimeout(() => cache.delete(key), ttl);
}

// api.js (modify fetchUser)
const cached = cache.get(`user:${id}`);
if (cached) return cached;
// ... existing fetch logic
cache.set(`user:${id}`, result, 60000);

Verification:

node -e "const c = require('./src/cache'); c.set('test', 42, 1000); console.log(c.get('test'));"
# Expected: 42

Estimated Time: 4 min

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Aws Fis Experiment Prepare

Use when the user wants to prepare, create, or generate an AWS FIS (Fault Injection Service) experiment configuration. Triggers on "prepare FIS experiment",...

Registry SourceRecently Updated
General

Aws Fis Experiment Execute

Use when the user wants to run a prepared AWS FIS experiment where the CloudFormation stack has already been deployed. Triggers on "execute FIS experiment",...

Registry SourceRecently Updated
General

Warranty Return Dispute Kit

Organizes a defective-product, denied-warranty, or return-window dispute into an evidence packet, timeline, support message, escalation script, contact log,...

Registry SourceRecently Updated
General

Goldman Sachs Co

提供高盛公司历史、业务模式、市场地位及关键数据,助力研究投资银行和金融机构角色分析。

Registry SourceRecently Updated